SEARCH · Engineering Papers

Results for “Agents”

Search indexed NASA NTRS and DOE OSTI research on propulsion, heat transfer, battery materials and energy systems. Follow report and document links to the original sources.

SourceResearch connectionFrom yearThrough year

Quote a phrase for an exact phrase match. Source license links do not imply unrestricted reuse.

At least 127 records · Page 7

All sources NASA NTRS DOE OSTI

DOE OSTI2023

Control of multi-agent systems: Results, open problems, and applications

The purpose of this review article is to present some recent results on the modeling and control of large systems of agents. We focus on particular applications where the agents are capable of independent actions instead of simply reacting to external forces. In the literature, such agents were referred to as autonomous, intelligent, self-propelled, greedy, and others. The main applications we have in mind are social systems (as opinion dynamics), pedestrians’ movements (also called crowd dynamics), animal groups, and vehicular traffic. We note that the last three examples include physical constraints; however, the agents are able to inject energy into the system, thus preventing the typical conservation of momentum and energy. In addition, the control problems posed by such systems are new and require innovative methods. We illustrate some ideas developed recently, including the use of sparse controls, limiting the total variation of controls, and defining new control problems for measures. After reviewing various approaches, we discuss some future research directions of potential interest. The latter encompasses both new types of equations and new types of limiting procedures to connect several scales at which a system can be represented. We conclude by illustrating a recent real-life experiment using autonomous vehicles on an open highway to smooth traffic waves. This opens the door to a new era of interventions to control real-time multi-agent systems and to increase the societal impact of such interventions guided by control research.

97 MATHEMATICS AND COMPUTING↗

DOE OSTI2020

Janus: A Python Package for Agent-Based Modeling of Land Use and Land Cover Change

Janus is an open source Python package for agent-based modeling (ABM) of land use and land cover change (LULCC). Many ABMs of LULCC have been created across platforms, some of which are not ideal for large scale, high resolution scenarios. This model provides a simple object-oriented framework for creating ABMs specific to LULCC. The organizational philosophy of the modeling framework is to create software objects (agents) that are associated with specific and contextual attributes which are isolated from where those agents exist in the spatial setting of the model, yet provide clear linkages between the agent, their environment, and other agents in the simulation. In this way, the framework allows for assembly of LULCC ABMs with low (programmatic) overhead, making the models extensible and providing clear mechanisms for integrating them with process-oriented biophysical models. Provided with Janus is a suite of geospatial data preprocessing tools that can use arbitrary land cover products as an input. Crop choice decisions are based on potential crop prices, these can be created synthetically, or drawn from integrated human-Earth systems models such as the GCAM. Janus is publicly accessible through GitHub and provides an example dataset for testing.

54 ENVIRONMENTAL SCIENCES↗

DOE OSTI2021

Challenges to detection: Humidity as a spur to chemical agent change

Detecting chemical agents in outdoor environments such as a battlefield is made challenging by not only the spurious signatures from background chemicals and surfaces (e.g. asphalt, dirt, concrete), but also by the chemical transformation of the actual agents. The change of CW agents to other species can be catalyzed by other chemicals present in the scene, by different substrates, as well as by local weather conditions. Some of the final environmental transformation products are known (e.g. for the G agents methylphosphonic acid), but many of the intermediate chemical states are not, nor are the rates of transformation to the other intermediates or the end products. In this study we have made preliminary optical investigations into the degradation products of a G-agent intermediate, namely methylphosphonic anhydride and its rate of conversion to the more stable methylphosphonic acid. Using infrared and Raman spectroscopies, we have found that the relative humidity (RH) greatly affects the rate of change and we report first results from these studies.

: chemical warfare agent detection, Methylphosphon↗

DOE OSTI2020

Role of Capping Agents in the Synthesis of Salicylate-Capped Zinc Oxide Nanoparticles

Capping agents are often used for controlling the size, aggregation, and properties of nanoparticles. To guide the design of improved nanomaterials for targeted performance, one can use mechanistic insights into the interactions between capping agents and nanoparticles. Here, we employ density functional theory (DFT), reactive force-field molecular dynamics (ReaxFF MD) simulations, and optical spectroscopy to study the interactions between salicylate, as a model capping agent, and zinc oxide (ZnO) nanoparticles. In this work, we find that salicylate strongly interacts with the nanoparticle via the formation of O–Zn bonds in a distorted six-membered coordination ring structure. We describe the mechanisms of capping of ZnO nanoparticles by salicylate via three different binding modes. Simulations indicate that salicylate undergoes dissociative adsorption at the highly active surface Zn sites via a hydrogen-transfer process, thereby forming a tridentate configuration. The water-mediated interaction also facilitates the dissociative adsorption, leading to two salicylate O atoms coordinating with a surface Zn atom, while the other salicylate O atom bonds with another surface Zn atom. For molecular adsorption, binding free energies indicate that salicylate binds more strongly to ZnO, often in a bidentate configuration, than water does. The formation of the salicylate–ZnO complex is substantiated by UV–visible and Fourier transform infrared spectra. We find that the C=O stretching mode of salicylate becomes softened when it interacts with the nanoparticle, suggesting chemisorption of salicylate on ZnO. Although DFT predicts strong interaction between salicylate and ZnO, ReaxFF MD simulation indicates the moderate interaction between these two components in aqueous solution. Water molecules in close contact with the nanoparticle surface undergo dissociation, thus resulting in a surface hydroxyl, a reactive oxygen species that may influence the nanoparticle’s catalytic properties. Overall, the atomic-level information provided here can guide the selection process of salicylate as an appropriate agent for ZnO nanoparticle synthesis when strong interactions of particles with capping agents are required.

37 INORGANIC, ORGANIC, PHYSICAL, AND ANALYTICAL CH↗

DOE OSTI2021

Assessing Adaptive Irrigation Impacts on Water Scarcity in Nonstationary Environments—A Multi‐Agent Reinforcement Learning Approach

Abstract One major challenge in water resource management is to balance the uncertain and nonstationary water demands and supplies caused by the changing anthropogenic and hydroclimate conditions. To address this issue, we developed a reinforcement learning agent‐based modeling (RL‐ABM) framework where agents (agriculture water users) are able to learn and adjust water demands based on their interactions with the water systems. The intelligent agents are created by a reinforcement learning algorithm adapted from the Q‐learning algorithm. We illustrated this framework in a case study where the RL‐ABM is two‐way coupled with the Colorado River Simulation System (CRSS), a long‐term planning model used for the administration of the Colorado River Basin, for assessing agriculture water uses impacts on water scarcity. Seventy‐eight intelligent agents are simulated, which can be grouped into three categories based on their parameter values: the “aggressive” (swift actions; low regrets), the “forward‐looking conservative” (mild actions; high regrets; fast learning), and the “myopic conservative” (mild actions; median regrets; slow learning). The ABM‐CRSS results showed that the major reservoirs in the Upper Colorado Basin might experience more frequent water shortages due to the increasing water uses compared to the original CRSS results. If the drought continues, the case study also demonstrates that agents can learn and adjust their demands.

Hung, Fengwei↗

DOE OSTI2026

The ballad of LLM agents: philosophical reasoning for chemistry

Large language models (LLMs) show remarkable potential for scientific reasoning but often produce unreliable or scientifically unactionable outputs when faced with multi-step logic, domain grounding, and interpretability challenges, especially in complex fields like chemistry and materials science. Here, we introduce a framework of philosophical reasoning agents, inspired by canonical thinkers such as Socrates, Descartes, Kant, and Hume, to guide LLM behavior via structured prompt engineering. These agents embody distinct reasoning paradigms (dialectical inquiry, deductive logic, rule-based judgment, and empirical validation) and are evaluated across multiple chemistry subdomains, physical, analytical, general, inorganic, and organic chemistry, using the ChemBench benchmark. Our agentic prompting approach yields substantial accuracy gains on open-ended numerical chemistry questions, with gains of +11.5 percentage points for GPT-4o with Hume, +4.5 percentage points for GPT-5 with Kant, and +21.8 percentage points for GPT-5.1 with Socrates at the strict 1% error threshold, relative to the corresponding base models. Beyond accuracy, we observe benchmark-level model–agent performance patterns, suggesting that different prompting styles interact differently with each base model. These findings demonstrate that embedding philosophy-of-science principles into multi-agent frameworks can improve and produce interpretable, adaptive, and domain-aligned scientific LLMs.

Harb, Hassan [Argonne National Laboratory (ANL), A↗

DOE OSTI2026

NeuDiff Agent: a governed AI workflow for single-crystal neutron crystallography

Large-scale facilities increasingly face analysis and reporting latency as a limiting step in scientific throughput, particularly for structural studies that require iterative reduction, integration, refinement and validation. To improve the time to result and analysis efficiency, NeuDiff Agent is introduced as a governed, tool-using AI workflow for TOPAZ at the Spallation Neutron Source. NeuDiff Agent takes instrument data through reduction, integration, refinement and validation to a validated crystal structure and a publication-ready CIF. NeuDiff Agent coordinates established crystallographic tools under explicit governance by restricting actions to allowlisted tools, enforcing fail-closed verification gates at key workflow boundaries, and capturing complete provenance for inspection, auditing and controlled replay. The present benchmark is limited to structural crystallography for periodic structures; magnetic structure analysis and incommensurate or superspace refinement are outside the scope of the current workflow. Performance is assessed using a fixed prompt protocol and repeated end-to-end runs with two large language model backends, with user and machine time partitioned and intervention burden and recovery behaviors quantified under gating. In a reference-case benchmark, NeuDiff Agent reduces wall time from 435 min (manual) to 86.5 ± 4.7 to 94.4 ± 3.5 min (4.6–5.0× faster) while producing a validated CIF with no checkCIF level A or B alerts. These results establish a practical route to deploy agentic AI in facility crystallography while preserving traceability and publication-facing validation requirements.

Xiao, Zhongcan [ORNL] (ORCID:0000000220761961)↗

DOE OSTI2023

Rutin is a potent senomorphic agent to target senescent cells and can improve chemotherapeutic efficacy

Aging is a major risk factor for most chronic disorders, for which cellular senescence is one of the central hallmarks. Senescent cells develop the pro-inflammatory senescence-associated secretory phenotype (SASP), which significantly contributes to organismal aging and age-related disorders. Development of senotherapeutics, an emerging class of therapeutic agents to target senescent cells, allows to effectively delay aging and alleviate chronic pathologies. Here we report preliminary outputs from screening of a natural medicinal agent (NMA) library for senotherapeutic candidates and validated several agents with prominent potential as senomorphics. Rutin, a phytochemical constituent found in a number of plants, showed remarkable capacity in targeting senescent cells by dampening expression of the full spectrum SASP. Further analysis indicated that rutin restrains the acute stress-associated phenotype (ASAP) by specifically interfering with the interactions of ATM with HIF1α, a master regulator of cellular and systemic homeostasis activated during senescence, and of ATM with TRAF6, part of a key signaling axis supporting the ASAP development toward the SASP. Conditioned media produced by senescent stromal cells enhanced the malignant phenotypes of prostate cancer cells, including in vitro proliferation, migration, invasion, and more importantly, chemoresistance, while rutin remarkably downregulated these gain-of-functions. Although classic chemotherapy reduced tumor progression, the treatment outcome was substantially improved upon combination of a chemotherapeutic agent with rutin. Our study provides a proof of concept for rutin as an emerging natural senomorphic agent, and presents an effective therapeutic avenue for alleviating age-related pathologies including cancer.

60 APPLIED LIFE SCIENCES↗

DOE OSTI2025

Meta Biome: a multiscale model integrating agent-based and metabolic networks to reveal spatial regulation in gut mucosal microbial communities

ABSTRACT Mucosal microbial communities (MMCs) are complex ecosystems near the mucosal layers of the gut essential for maintaining health and modulating disease states. Despite advances in high-throughput omics technologies, current methodologies struggle to capture the dynamic metabolic interactions and spatiotemporal variations within MMCs. In this work, we presentMetaBiome, a multiscale model integrating agent-based modeling (ABM), finite volume methods, and constraint-based models to explore the metabolic interactions within these communities. Integrating ABM allows for the detailed representation of individual microbial agents each governed by rules that dictate cell growth, division, and interactions with their surroundings. Through a layered approach—encompassing microenvironmental conditions, agent information, and metabolic pathways—we simulated different communities to showcase the potential of the model. Using ourin-silicoplatform, we explored the dynamics and spatiotemporal patterns of MMCs in the proximal small intestine and the cecum, simulating the physiological conditions of the two gut regions. Our findings revealed how specific microbes adapt their metabolic processes based on substrate availability and local environmental conditions, shedding light on spatial metabolite regulation and informing targeted therapies for localized gut diseases.MetaBiome provides a detailed representation of microbial agents and their interactions, surpassing the limitations of traditional grid-based systems. This work marks a significant advancement in microbial ecology, as it offers new insights into predicting and analyzing microbial communities. IMPORTANCE Our study presents a novel multiscale model that combines agent-based modeling, finite volume methods, and genome-scale metabolic models to simulate the complex dynamics of mucosal microbial communities in the gut. This integrated approach allows us to capture spatial and temporal variations in microbial interactions and metabolism that are difficult to study experimentally. Key findings from our model include the following: (i) prediction of metabolic cross-feeding and spatial organization in multi-species communities, (ii) insights into how oxygen gradients and nutrient availability shape community composition in different gut regions, and (iii) identification of spatiallyregulated metabolic pathways and enzymes inE. coli. We believe this work represents a significant advance in computational modeling of microbial communities and provides new insights into the spatial regulation of gut microbiome metabolism. The multiscale modeling approach we have developed could be broadly applicable for studying other complex microbial ecosystems.

Microbiology↗

DOE OSTI2021

PowerGridworld: A Framework for Multi-Agent Reinforcement Learning in Power Systems [SWR-22-07]

NREL's PowerGridworld provides a modular simulation environment for training heterogenous, grid-aware, multi-agent reinforcement learning (RL) policies at scale. The package enables the user to create component gym environments that can be composed into more complex agents. For example, a grid interactive building environment can be created by composing together component environments each encapsulating the building, PV, and battery physics. These multi-component environments can then be combined into multi-agent simulation where each agent's power consumption/injection becomes an input for solving the optimal power flow on a distribution feeder modeled in OpenDSS. Information from OpenDSS, such as bus voltages and line flows, can be included in the agents' observation spaces to enable grid-aware rewards. The default API for the PowerGridworld simulator conforms to RLLib's MultiAgent API and thus enables distributed training using HPC and cloud resources.

Biagioni, David↗

DOE OSTI2026

Building MCP-native hierarchical AI scientist ecosystems: a perspective on scaling multi-agent scientific discovery

Large language models (LLMs) are evolving from chatbots with limited tool-using capabilities to agentic AI systems that can perform deep research, assist in proposing hypotheses, help design experiments, automate data analysis, and draft scientific reports. However, there are currently two bottlenecks limiting LLMs' real-world impact on the broader scientific research community beyond academic demonstrations: lack of interoperability (repetitive manual tool-integration is required across scenarios) and the need for scalable coordination (unstructured communication and memory become brittle as the number of agents grows). In this Perspective, we argue that the next phase of agentic scientific discovery requires the development of an ecosystem of protocol-native agents and tools organized through hierarchies inspired by human society, beyond the current paradigm of a single monolithic “AI scientist”. We use Model Context Protocol (MCP) as a concrete example of an emerging interoperability layer for scientific tool and context exchange, and we propose three complementary pathways to increase the scaling capabilities of an MCP-native scientific ecosystem by addressing the composability issues: (1) MCP servers for high-value scientific tools maintained by domain experts, (2) automated transformation of existing code repositories into MCP services, and (3) autonomous invention and evolution of new agents and workflows. Finally, we provide a practical roadmap for scaling AI-driven scientific discovery by expanding tool supply and coordination in MCP-native scientific ecosystems.

97 MATHEMATICS AND COMPUTING↗

DOE OSTI2025

ADEPT: A Pedagogical Framework for Integrating Agentic AI with Deterministic Scientific Workflows

The integration of Large Language Models (LLMs) into scientific research promises to accelerate discovery, yet a significant gap remains between the dynamic reasoning of Artificial Intelligence (AI) agents and the static, deterministic nature of canonical scientific workflows. This paper introduces ADEPT (Agentic Discovery and Exploration Platform for Tools), a reference architecture and pedagogical framework explicitly designed to bridge this gap. ADEPT's primary mission is to provide a transparent, "glass-box" environment where researchers and engineers can learn to effectively wrap established scientific software (e.g., BLAST, Nextflow pipelines) and compose it into reliable, agent-driven workflows. We describe its modular, multi-server architecture, which leverages the Model Context Protocol (MCP) for tool serving, LangGraph for robust agentic orchestration, and a secure nsjail-based sandbox for safe code execution. By prioritizing architectural clarity, safety, and modularity, ADEPT serves as an extensible blueprint for building trustworthy AI-augmented systems and fosters the collaborative development necessary to responsibly employ agentic AI for science. We provide practical examples of how to adapt and extend this framework, highlighting its utility in workforce development and AI-readiness capabilities across research and development projects.

97 MATHEMATICS AND COMPUTING↗

NASA NTRS1972

Spacecraft sanitation agent development

The development of an effective sanitizing agent that is compatible with the spacecraft environment and the human occupant is discussed. Experimental results show that two sanitation agents must be used to satisfy mission requirements: one agent for personal hygiene and one for equipment maintenance. It was also recommended that a water rinse be used with the agents for best results, and that consideration be given to using the agents pressure packed or in aerosol formulations.

Source record↗

NASA NTRS1976

Further development of high temperature-resistant graphite fiber coupling agents

Potential coupling agents for graphite fibers were screened by their effect on the weight losses of Thornel 300, HMS, and HTS fibers at 588K for 200 and 400 hours. Unidirectional laminates were made from HMS and HTS fibers, untreated, and treated with each of the seven coupling agents. The matrix of all laminates was PMR polyimide (PMR-PR). On the basis of the best overall retention of elevated temperature interlaminar shear strength after 200 hours at 588K, composite weight after 200 hours at 588K, and fiber weight after 400 hours at 588K, ventromer T-1 applied from aqueous solution and pyrolyzed PPQ were selected for further evaluation as coupling agents for HTS fiber while ventromer T-2 and pyrolyzed PPQ were selected as coupling agents for HMS fiber. It was shown that pyrolyzed PPQ as a coupling agent improves the oxidative stability of HTS/PMR-PI composites.

Griffin, R. N.↗

NASA NTRS1989

Observational goals for Max '91 to identify the causative agent for impulsive bursts

Recent studies of impulsive hard x ray and microwave bursts suggest that a propagating causative agent with a characteristic velocity of the order of 1000 km/s is responsible for these bursts. The results of these studies are summarized and observable distinguishing characteristics of the various possible agents are highlighted, with emphasis on key observational goals for the Max '91 campaigns. The most likely causative agents suggested by the evidence are shocks, thermal conduction fronts, and propagating modes of magnetic reconnection in flare plasmas. With new instrumentation planned for Max '91, high spatial resolution observations of hard x ray sources have the potential to identify the agent by revealing detailed features of source spatial evolution. Observations with the Very Large Array and other radio imaging instruments are of great importance, as well as detailed modeling of coronal loop structures to place limits on their density and temperature profiles. With the combined hard x ray and microwave imaging observations, aided by loop model results, the simplest causative agent to rule out would be the propagating modes of magnetic reconnection. To fit the observational evidence, reconnection modes would need to travel at approximately the same velocity (the Alfven velocity) in different coronal structures that vary in length by a factor of 10(exp 3). Over such a vast range in loop lengths, it is difficult to believe that the Alfven velocity is constant. Thermal conduction fronts would be suggested by sources that expand along the direction of B and exhibit relatively little particle precipitation. Particle acceleration due to shocks could produce more diverse radially expanding source geometries with precipitation at loop footprints.

Batchelor, D. A.↗

NASA NTRS1990

Agent independent task planning

Agent-Independent Planning is a technique that allows the construction of activity plans without regard to the agent that will perform them. Once generated, a plan is then validated and translated into instructions for a particular agent, whether a robot, crewmember, or software-based control system. Because Space Station Freedom (SSF) is planned for orbital operations for approximately thirty years, it will almost certainly experience numerous enhancements and upgrades, including upgrades in robotic manipulators. Agent-Independent Planning provides the capability to construct plans for SSF operations, independent of specific robotic systems, by combining techniques of object oriented modeling, nonlinear planning and temporal logic. Since a plan is validated using the physical and functional models of a particular agent, new robotic systems can be developed and integrated with existing operations in a robust manner. This technique also provides the capability to generate plans for crewmembers with varying skill levels, and later apply these same plans to more sophisticated robotic manipulators made available by evolutions in technology.

Davis, William S.↗

NASA NTRS1989

Coordinating the activities of a planner and an execution agent

A research program was defined that will explore the link between planning and execution systems. A simple scenario was defined in which a very capable off-line planning system interacts with the user and a smaller, less capable, on-line real-time system executing plans and reacting to faults. However, the on-line execution system may have a more flexible representation of the plans it is executing. This imbalance in the capabilities of the two agents involved should clarify some of the research objectives and give an experimental framework for the work. The task is to investigate the knowledge representations and communication protocols needed to link a user stating some requirements for a task to be carried out through a planning system to the (remote) execution agent that can carry out the user's wishes. The notion that a single representation can encapsulate the expression of the user's requirements, the capabilities for action, the communication to the execution agent, the successful or faulty response from the execution agent and the means of keeping the user informed, is examined. Methods of creating plan patches to update the plans separately held by each of the parties involved to keep them in step as they each react to changing circumstances in real-time is investigated. This involves the specification of plan patch attachment points that can be understood by the recipient. Transaction based methods are also investigated for coordinating the activities of the planner with those of the execution agent and user. The trial application area for the research is in the command and control of an advanced Earth Observation Space Platform.

Tate, Austin↗

NASA NTRS1991

Enhancement of biological control agents for use against forest insect pests and diseases through biotechnology

Research and development efforts in our research group are focused on the generation of more efficacious biological control agents through the techniques of biotechnology for use against forest insect pests and diseases. Effective biological controls for the gypsy moth and for tree fungal wilt pathogens are under development. The successful use of Gypchek, a formulation of the Lymantria dispar nuclear polyhedrosis virus (LdNPV), in gypsy moth control programs has generated considerable interest in that agent. As a consequence of its specificity, LdPNV has negligible adverse ecological impacts compared to most gypsy moth control agents. However, LdNPV is not competitive with other control agents in terms of cost and efficacy. We are investigating several parameters of LdNPV replication and polyhedra production in order to enhance viral potency and efficacy thus mitigating the current disadvantages of LdNPV for gypsy moth control, and have identified LdNPV variants that will facilitate these efforts. Tree endophytic bacteria that synthesize antifungal compounds were identified and an antibiotic compound from one of these bacteria was characterized. The feasibility of developing tree endophytes as biological control agents for tree vascular fungal pathogens is being investigated.

Slavicek, James M.↗